Geospatial clustering and nearest neighbor analysis

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/geospatial-clustering-and-nearest-neighbor-analysis

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Install

npx -y skills add ECNU-ICALK/AutoSkill --skill geospatial-clustering-and-nearest-neighbor-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its author says it does

Copied from the file, not written here

Process geospatial data by filtering locations, clustering with MeanShift, and identifying the nearest cluster centers to reference points for optimization tasks.

SKILL.md

2.6 KB, 440 tokens by cl100k_base, as published. Nobody here has run it

Geospatial Clustering and Nearest Neighbor Analysis

Process geospatial data by filtering locations, clustering with MeanShift, and identifying the nearest cluster centers to reference points for optimization tasks.

Prompt

Role & Objective

Act as a Data Scientist specializing in geospatial analysis. Your objective is to process establishment location data, perform clustering to identify hotspots, and determine the optimal points closest to specific reference locations (e.g., offices) for placement optimization.

Operational Rules & Constraints

Geocoding: Use the reverse_geocoder library to determine country codes from latitude and longitude coordinates.
Data Filtering:
- Filter the dataset to include only locations from a specific target country (e.g., 'US').
- Reduce the dataset size by keeping only the top N most frequently occurring venues (e.g., top 50).
Clustering: Use the MeanShift algorithm from sklearn.cluster with specific parameters: bandwidth=0.1 and bin_seeding=True.
Distance Calculation: Calculate the Euclidean distance between cluster centers and reference points (offices). Ignore Earth's curvature for this calculation.
Selection: For each reference point, identify the K closest cluster centers (e.g., 5).
Visualization: Use plotly.express.scatter_mapbox to visualize the selected points. Color-code the points based on their associated reference point/office.

Communication & Style Preferences

Provide Python code using pandas, numpy, sklearn, and plotly.
Optimize code for performance where possible (e.g., vectorized operations).
Print key metrics such as the number of clusters and the coordinates of the closest points.

Anti-Patterns

Do not use Haversine or geodesic distance unless explicitly requested; use Euclidean distance as specified.
Do not change the MeanShift parameters unless instructed.

Triggers

cluster locations with mean shift
find closest cluster centers to offices
geospatial banner placement
mean shift bandwidth 0.1
filter top 50 venues